import numpy as np
import pandas as pd
import plotly.express as px
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS 
import matplotlib.pyplot as plt 

gun_data = pd.read_csv("gun-violence-data.csv")
gun_data.head()

Data Cleaning

columns_drop = ["incident_url", "source_url", "incident_url_fields_missing", "address", "participant_status", "sources", "latitude", "longitude", "state_house_district", "state_senate_district", "incident_id", "participant_name", "notes","location_description","congressional_district"]

gun_data.drop(columns_drop, axis=1, inplace = True)
#gun_data.dropna(inplace=True)
gun_data.reset_index(drop=True, inplace=True)

gun_data.head(10)

words = ' '.join(i for i in gun_data['notes'].str.split(expand=True).stack().values.tolist())
stopwords = set(STOPWORDS) 
wordcloud = WordCloud(width = 800, height = 800, 
                background_color ='white', 
                stopwords = stopwords, 
                min_font_size = 10).generate(words) 
  
# plot the WordCloud image                        
plt.figure(figsize = (8, 8), facecolor = None) 
plt.imshow(wordcloud) 
plt.axis("off") 
plt.tight_layout(pad = 0) 
  
plt.show() 

# initialize the columns
gun_data['Adult'] = 0
gun_data['Teen'] = 0
gun_data['Child'] = 0

gun_data['Male'] = 0
gun_data['Female'] = 0

def age_Sorter(Row):
    temp = Row['participant_age_group']
    if str(temp) == 'nan':
        return Row
    age_group = temp.split("||")
    if len(age_group) == 1:
        age_group = age_group[0].split("|")
    for age in age_group:
        a = age.split("::")
        if len(a) == 1:
            a = a[0].split(":")
        if a[1] == "Adult 18+":
            Row['Adult'] += 1
        elif a[1] == "Teen 12-17":
            Row['Teen'] += 1
        else:
            Row['Child'] += 1
    for col in gun_data.columns:
        if col == 'participant_age_group':
            columns_drop = 'participant_age_group'
        return Row


def gender_Sorter(Row):
    temp = Row['participant_gender']
    if str(temp) == 'nan':
        return Row
    gender = temp.split("||")
    if len(gender) == 1:
        gender = gender[0].split("|")
    for gen in gender:
        g = gen.split("::")
        if len(g) == 1:
            g = g[0].split(":")
        if g[1] == "Male":
            Row['Male'] += 1
        elif g[1] == "Female":
            Row['Female'] += 1
    for col in gun_data.columns:
        if col == 'participant_gender':
            columns_drop = 'participant_gender'
    return Row

gun_data = gun_data.apply(age_Sorter, axis = 1)
gun_data = gun_data.apply(gender_Sorter, axis = 1)
gun_data.head()

Lcol = []
for col in gun_data.columns:
    if col == 'participant_gender':
        col = 'nan'
    else:
        Lcol.append(col)

Dylan's

# add state code to states
violence_data = pd.read_csv("gun-violence-data.csv")

states = {
    'Alabama': 'AL',
    'Alaska': 'AK',
    'American Samoa': 'AS',
    'Arizona': 'AZ',
    'Arkansas': 'AR',
    'California': 'CA',
    'Colorado': 'CO',
    'Connecticut': 'CT',
    'Delaware': 'DE',
    'District of Columbia': 'DC',
    'Florida': 'FL',
    'Georgia': 'GA',
    'Guam': 'GU',
    'Hawaii': 'HI',
    'Idaho': 'ID',
    'Illinois': 'IL',
    'Indiana': 'IN',
    'Iowa': 'IA',
    'Kansas': 'KS',
    'Kentucky': 'KY',
    'Louisiana': 'LA',
    'Maine': 'ME','Maryland': 'MD',
    'Massachusetts': 'MA',
    'Michigan': 'MI',
    'Minnesota': 'MN',
    'Mississippi': 'MS',
    'Missouri': 'MO',
    'Montana': 'MT',
    'Nebraska': 'NE',
    'Nevada': 'NV',
    'New Hampshire': 'NH',
    'New Jersey': 'NJ',
    'New Mexico': 'NM',
    'New York': 'NY',
    'North Carolina': 'NC',
    'North Dakota': 'ND',
    'Northern Mariana Islands':'MP',
    'Ohio': 'OH',
    'Oklahoma': 'OK',
    'Oregon': 'OR',
    'Pennsylvania': 'PA',
    'Puerto Rico': 'PR',
    'Rhode Island': 'RI',
    'South Carolina': 'SC',
    'South Dakota': 'SD',
    'Tennessee': 'TN',
    'Texas': 'TX',
    'Utah': 'UT',
    'Vermont': 'VT','Virgin Islands': 'VI',
    'Virginia': 'VA',
    'Washington': 'WA',
    'West Virginia': 'WV',
    'Wisconsin': 'WI',
    'Wyoming': 'WY'
}

violence_data['state code'] = violence_data['state'].apply(lambda x : states[x])
ViolenceChart = violence_data.groupby('state code')[['n_killed', 'n_guns_involved']].sum().sort_values(by = "n_killed",ascending = False).reset_index().head(25)
ViolenceChart.plot.pie(y="n_guns_involved")

fig = px.choropleth(violence_data.groupby('state code')['n_killed'].sum().reset_index(), locations='state code', locationmode="USA-states", color='n_killed', scope="usa", color_continuous_scale="Viridis")
fig.show()

If the shooter is an adult, there will be a greater amount of weapons used.

gun_data_edited = pd.read_csv("gun-violence-data.csv")
columns_drop_two = ["incident_url", "source_url", "incident_url_fields_missing", "address", "participant_status", "sources", "latitude", "longitude", "state_house_district", "state_senate_district", "incident_id", "participant_name", "notes","location_description","congressional_district"]

gun_data_edited.drop(columns_drop_two, axis=1, inplace = True)
#gun_data.dropna(inplace=True)
gun_data_edited.reset_index(drop=True, inplace=True)

gun_data_edited['Adult'] = 0
gun_data_edited['Teen'] = 0
gun_data_edited['Child'] = 0

gun_data_edited['Male'] = 0
gun_data_edited['Female'] = 0

def age_Sorter_Two(Row):
    temp = Row['participant_age_group']
    if str(temp) == "nan":
        return Row
    #print(temp)
    age_group = temp.split("||")
    if len(age_group) == 1:
        age_group = age_group[0].split("|")
    for age in age_group:
        a = age.split("::")
        if len(a) == 1:
            a = a[0].split(":")
        if a[1] == "Adult 18+":
            Row['Adult'] += 1
        elif a[1] == "Teen 12-17":
            Row['Teen'] += 1
        else:
            Row['Child'] += 1
    for col in gun_data_edited.columns:
        if col == 'participant_age_group':
            columns_drop = 'participant_age_group'
        return Row


def gender_Sorter_Two(Row):
    temp = Row['participant_gender']
    if str(temp) == "nan":
        return Row
    gender = temp.split("||")
    if len(gender) == 1:
        gender = gender[0].split("|")
    for gen in gender:
        g = gen.split("::")
        if len(g) == 1:
            g = g[0].split(":")
        if g[1] == "Male":
            Row['Male'] += 1
        elif g[1] == "Female":
            Row['Female'] += 1
    for col in gun_data_edited.columns:
        if col == 'participant_gender':
            columns_drop = 'participant_gender'
    return Row




gun_data_edited = gun_data_edited.apply(age_Sorter_Two, axis = 1)
gun_data_edited = gun_data_edited.apply(gender_Sorter_Two, axis = 1)
gun_data_edited.head()

#adultNumOfGun = px.scatter(gun_data_edited, x="Adult", y="n_guns_involved")
#adultNumOfGun.show()

#Create a histogram of another column of your choice below.
gun_data_edited.hist('Adult')

gun_data_edited.head(30)

tempTwo = row['n_guns_involved']
for 
if str(TempTwo) == "nan":
    pass
else:
    gun_data_edited['n_guns_involved'].astype(int)

gun_data_edited.head()

#The correlation between the state the shooting happend in and the amount of injured people. (Kathryn)

gun_info = pd.read_csv("gun-violence-data.csv")
columns_drop = ["incident_url", "source_url", "incident_url_fields_missing", "address", "participant_status", "sources", "latitude", "longitude", "state_house_district", "state_senate_district", "incident_id", "participant_name", "notes","location_description","congressional_district"]

gun_info.drop(columns_drop, axis=1, inplace = True)
gun_info.reset_index(drop=True, inplace=True)
gun_info.head()

gun_info.info()

fig = px.scatter(gun_info, x = "state", y = "n_killed")
fig.show()

fig = px.scatter(gun_info, x = "state", y = "n_injured")
fig.show()

When a teen or adult is able to posses a firearm without owning it, it will result in a shooting.(Logan)

gun_relation = pd.read_csv("gun-violence-data.csv")

columns_drop = ["incident_url", "source_url", "incident_url_fields_missing", "address", "participant_status", "sources", "latitude", "longitude", "state_house_district", "state_senate_district", "incident_id", "participant_name", "notes","location_description","congressional_district"]

gun_relation.drop(columns_drop, axis=1, inplace = True)
#gun_relation.dropna(inplace=True)
gun_relation.reset_index(drop=True, inplace=True)

gun_relation['Adult'] = 0
gun_relation['Teen'] = 0
gun_relation['Child'] = 0

def age_Sorter2(Row):
    temp = Row['participant_age_group']
    if str(temp) == "nan":
        return Row
    age_group = temp.split("||")
    if len(age_group) == 1:
        age_group = age_group[0].split("|")
    for age in age_group:
        a = age.split("::")
        if len(a) == 1:
            a = a[0].split(":")
        if a[1] == "Adult 18+":
            Row['Adult'] += 1
        elif a[1] == "Teen 12-17":
            Row['Teen'] += 1
        else:
            Row['Child'] += 1
    for col in gun_relation.columns:
        if col == 'participant_age_group':
            columns_drop = 'participant_age_group'
        return Row
gun_relation = gun_relation.apply(age_Sorter2, axis = 1)

gun_relation.head()

import plotly.express as px  
teen_shooting = px.scatter(gun_relation, x='n_killed', y='Teen')
teen_shooting.show()

import plotly.express as px  
teen_shooting_injury = px.scatter(gun_relation, x='n_injured', y='Teen')
teen_shooting_injury.show()

gun_relation['Adult'].unique()

import plotly.express as px
adult_shooting_injury = px.bar(gun_relation, x='n_injured', y='Adult')
adult_shooting_injury.show()

import plotly.express as px  
adult_shooting = px.scatter(gun_relation, x='n_killed', y='Adult')
adult_shooting.show()

plt.style.use("fivethirtyeight")
plt.figure(figsize=(30, 10))
plt.xlabel("Date")
plt.ylabel("Values")
plt.title("Sample Time Series Plot")
plt.plot(gun_data["n_killed"])

period_length = 5
start_year = 2013
end_year = 2018
df = df[(df['YEAR'] >= start) & (df['YEAR'] <= 2019)]